| { | |
| "epoch": 3.0, | |
| "eval_logits/chosen": -3.1037471294403076, | |
| "eval_logits/rejected": -3.058722734451294, | |
| "eval_logps/chosen": -541.3610229492188, | |
| "eval_logps/rejected": -421.7948913574219, | |
| "eval_loss": 0.6159699559211731, | |
| "eval_rewards/accuracies": 0.6765000224113464, | |
| "eval_rewards/chosen": -0.9541231393814087, | |
| "eval_rewards/margins": 1.1325011253356934, | |
| "eval_rewards/rejected": -2.0866243839263916, | |
| "eval_runtime": 348.052, | |
| "eval_samples": 2000, | |
| "eval_samples_per_second": 5.746, | |
| "eval_steps_per_second": 2.873, | |
| "train_loss": 0.6616154855680051, | |
| "train_runtime": 49213.1151, | |
| "train_samples": 61966, | |
| "train_samples_per_second": 3.777, | |
| "train_steps_per_second": 0.472 | |
| } |